Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

Dataset: 80% C4 (Web Text) and 20% Python Code

Neuron 1960 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 4.0395. Min Range: -4.0395

Max Act: 4.0395. Min Act: -0.0000

Data Index: 933960 (C4 (Web Text))

Max Activating Token Index: 1000

Text #1

Max Range: 4.0395. Min Range: -4.0395

Max Act: 3.7958. Min Act: -0.0000

Data Index: 1159204 (C4 (Web Text))

Max Activating Token Index: 975

Text #2

Max Range: 4.0395. Min Range: -4.0395

Max Act: 3.9173. Min Act: -0.0000

Data Index: 1229252 (C4 (Web Text))

Max Activating Token Index: 882

Text #3

Max Range: 4.0395. Min Range: -4.0395

Max Act: 3.9020. Min Act: -0.0000

Data Index: 1335256 (C4 (Web Text))

Max Activating Token Index: 326

Text #4

Max Range: 4.0395. Min Range: -4.0395

Max Act: 3.6375. Min Act: -0.0000

Data Index: 1261258 (C4 (Web Text))

Max Activating Token Index: 471

Text #5

Max Range: 4.0395. Min Range: -4.0395

Max Act: 3.6095. Min Act: -0.0000

Data Index: 471837 (C4 (Web Text))

Max Activating Token Index: 166

Text #6

Max Range: 4.0395. Min Range: -4.0395

Max Act: 3.6487. Min Act: -0.0000

Data Index: 574464 (C4 (Web Text))

Max Activating Token Index: 795

Text #7

Max Range: 4.0395. Min Range: -4.0395

Max Act: 3.4356. Min Act: -0.0000

Data Index: 1247533 (C4 (Web Text))

Max Activating Token Index: 344

Text #8

Max Range: 4.0395. Min Range: -4.0395

Max Act: 3.5238. Min Act: -0.0000

Data Index: 1290477 (C4 (Web Text))

Max Activating Token Index: 84

Text #9

Max Range: 4.0395. Min Range: -4.0395

Max Act: 3.2866. Min Act: -0.0000

Data Index: 431614 (C4 (Web Text))

Max Activating Token Index: 554

Text #10

Max Range: 4.0395. Min Range: -4.0395

Max Act: 3.2415. Min Act: -0.0000

Data Index: 539229 (C4 (Web Text))

Max Activating Token Index: 392

Text #11

Max Range: 4.0395. Min Range: -4.0395

Max Act: 3.3889. Min Act: -0.0000

Data Index: 1349308 (C4 (Web Text))

Max Activating Token Index: 529

Text #12

Max Range: 4.0395. Min Range: -4.0395

Max Act: 2.9029. Min Act: -0.0000

Data Index: 575275 (C4 (Web Text))

Max Activating Token Index: 211

Text #13

Max Range: 4.0395. Min Range: -4.0395

Max Act: 2.9429. Min Act: -0.0000

Data Index: 198740 (C4 (Web Text))

Max Activating Token Index: 664

Text #14

Max Range: 4.0395. Min Range: -4.0395

Max Act: 2.8999. Min Act: -0.0000

Data Index: 1048682 (C4 (Web Text))

Max Activating Token Index: 487

Text #15

Max Range: 4.0395. Min Range: -4.0395

Max Act: 2.8989. Min Act: -0.0000

Data Index: 1258378 (C4 (Web Text))

Max Activating Token Index: 830

Text #16

Max Range: 4.0395. Min Range: -4.0395

Max Act: 2.8298. Min Act: -0.0000

Data Index: 443976 (C4 (Web Text))

Max Activating Token Index: 196

Text #17

Max Range: 4.0395. Min Range: -4.0395

Max Act: 2.6592. Min Act: -0.0000

Data Index: 526409 (C4 (Web Text))

Max Activating Token Index: 864

Text #18

Max Range: 4.0395. Min Range: -4.0395

Max Act: 2.6176. Min Act: -0.0000

Data Index: 1153468 (C4 (Web Text))

Max Activating Token Index: 923

Text #19

Max Range: 4.0395. Min Range: -4.0395

Max Act: 2.6674. Min Act: -0.0000

Data Index: 443254 (C4 (Web Text))

Max Activating Token Index: 122